Learning discriminative spatial representation for image classification - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2011

Learning discriminative spatial representation for image classification


Spatial Pyramid Representation (SPR) [7] introduces spatial layout information to the orderless bag-of-features (BoF) representation. SPR has become the standard and has been shown to perform competitively against more complex methods for incorporating spatial layout. In SPR the image is divided into regular grids. However, the grids are taken as uniform spatial partitions without any theoretical motivation. In this paper, we address this issue and propose to learn the spatial partitioning with the BoF representation. We define a space of grids where each grid is obtained by a series of recursive axis aligned splits of cells. We cast the classification problem in a maximum margin formulation with the optimization being over the weight vector and the spatial grid. In addition to experiments on two challenging public datasets (Scene-15 and Pascal VOC 2007) showing that the learnt grids consistently perform better than the SPR while being much smaller in vector length, we also introduce a new dataset of human attributes and show that the current method is well suited to the recognition of spatially localized human attributes.
Fichier principal
Vignette du fichier
bmvc_final.pdf (2.65 Mo) Télécharger le fichier
Vignette du fichier
grid_over_pics4x4.jpg (389.28 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Format : Figure, Image

Dates and versions

hal-00722820 , version 1 (04-08-2012)



Gaurav Sharma, Frédéric Jurie. Learning discriminative spatial representation for image classification. BMVC 2011 - British Machine Vision Conference, Aug 2011, Dundee, United Kingdom. pp.1-11, ⟨10.5244/C.25.6⟩. ⟨hal-00722820⟩
668 View
685 Download



Gmail Facebook X LinkedIn More